GitsSaikat/Guardian-Agent
Improving AI Systems with Self-Defense Mechanisms
This project helps AI system developers protect their AI models from malicious prompts that try to hijack or manipulate their behavior. It takes in user prompts and ensures the AI model only acts on legitimate, safe instructions, preventing it from being 'jailbroken' or manipulated. Developers building AI agents who want to maintain strict control over their AI's responses and actions would use this.
No commits in the last 6 months.
Use this if you are developing an AI agent and need to build in robust self-defense mechanisms against adversarial prompt attacks and jailbreaking attempts.
Not ideal if you are an end-user of an existing AI system, as this tool is for developers to integrate into their AI agent's architecture.
Stars
23
Forks
8
Language
Python
License
MIT
Category
Last pushed
Feb 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/GitsSaikat/Guardian-Agent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
Dicklesworthstone/destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being...
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...
Pro-GenAI/Agent-Action-Guard
🛡️ Safe AI Agents through Action Classifier